Skip to main content
Keep the Domain IDs and executor configuration from the preceding guides. A new process or simulator reset does not require a new learner. Reconnect to the existing Domain, inspect its trajectory state, and continue with the same coordinate meanings, timing, action bounds, and outcome definition.

​
Save the integration manifest

Retain credentials separately. An execution-record export transfers acquired executions into a structural stage; it is not a whole-Domain backup or a general restore format. Keep the original Domains available when you intend to continue learning from them.

​
Execute an acquired sequence without learning

The acquisition request schema supports mode: "frozen". Use the same current-state and goal arrays as acquisition, then execute the returned sequence with the same adapter. Save physical results locally without sending a training observation.
This snippet reuses finite_matrix and the adapter hooks from Sequence acquisition. evaluation_reset_key identifies a saved evaluation scenario. Keep evaluation contexts separate from acquisition contexts when you want to assess behavior on new conditions. Frozen mode does not guarantee that the retained behavior completes the task.

​
Execute a selected base or retained correction

To use a structural result, execute the preserved base_execution["actions"] with its original adapter. The structural guide’s execute_candidate already applies the shared cadence, padding, and completion rule. For a contextual correction, call evaluate with the measured context only:
POST to https://rei-neuroadapt-api.reilabs.org/api/v1/domains/{refinement_domain}/trajectory/evaluate. Replace the illustration with [target_x, target_y, initial_vx, initial_vy] measured for the current reset. Omit decision_id and candidate_index for retained use. Those two fields select a candidate within a pending training comparison. Use the returned offsets with the exact selected base, compose and bound the actions as shown in Contextual refinement, and record the resulting execution locally. Do not configure a new refinement Domain for each context. The reference client compares the refinement state’s fingerprint before and after retained evaluation and sends no observe calls. That checks the state exposed by the refinement mechanism; also keep the base and executor manifest unchanged.

​
Record intent before each mutation

For configure, exploratory propose, and observe, durably record the intended request before sending it. After a response, save the returned IDs and receipt. Between proposal and observation, persist the physical execution and its measured outcomes first. All trajectory routes use POST, including reads such as state and records. Decide retry behavior from the operation’s role, not from the HTTP verb alone. A request_id is useful for correlation; the reference schema does not promise that repeating it deduplicates a mutation. To cancel a known pending decision:
If you cannot determine whether a mutation was applied, pause that Domain’s writer and resolve the ambiguity from the service’s available state or operational records. Generating new IDs or replaying physical actions can make an uncertain operation harder to reconcile. trajectory/reset is not a retry mechanism: it resets learner state. Structural intervention: "deletion" instead tests removing commands from an acquired execution.

​
Check requests before a long run

Use the same production base, Unit API Key, and mechanism that the run will use. Start with a fresh owned Domain and a small, measured acquisition or complete candidate/context comparison. Confirm configuration, returned IDs, array dimensions, observation acknowledgement, and subsequent readable state before increasing the budget. The shared helper rejects non-finite JSON and bodies over the reference 1 MiB limit. For comparisons, plan the full candidate count times context count before physical execution. Keep one writer per example Domain, finish pending work before exporting, and keep a durable record of every stage handoff.